小白的自我救贖
Neural networks can be constructed using the torch.nn package
An nn.Module contains layers, and a method forward(input)that returns the output即兩部分組成：構建網(wǎng)絡層猾编，已經(jīng)輸入接口forward函數(shù)蒸其，用于前向傳播
Define a network：
import torch
import torch.nn as nn
import torch.nn.functional as F
class Net(nn.Module):#pythorch固有形式
def __init__(self):#__init__方法的第一個參數(shù)永遠是self桃移，表示創(chuàng)建的實例本身茅主。因此，在__init__方法內(nèi)部祟剔，就可以把各種屬性綁定到self映挂，因為self就指向創(chuàng)建的實例本身鞭莽。
super(Net, self).__init__()
# 1 input image channel, 6 output channels, 3x3 square convolution
# kernel
self.conv1 = nn.Conv2d(1, 6, 3)
self.conv2 = nn.Conv2d(6, 16, 3)
# an affine operation: y = Wx + b
self.fc1 = nn.Linear(16 * 6 * 6, 120) # 6*6 from image dimension
self.fc2 = nn.Linear(120, 84)
self.fc3 = nn.Linear(84, 10)#以上代碼即為構建網(wǎng)絡層部分
#**注意：參數(shù)只涉及到網(wǎng)絡中卷積核數(shù)目、大小等參數(shù)唐断，不涉及輸入圖像大小
#以下代碼為forward函數(shù)选脊、前向傳播部分
def forward(self, x):
# Max pooling over a (2, 2) window
x = F.max_pool2d(F.relu(self.conv1(x)), (2, 2))
# If the size is a square you can only specify a single number
x = F.max_pool2d(F.relu(self.conv2(x)), 2)
x = x.view(-1, self.num_flat_features(x))#拉成向量
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
x = self.fc3(x)
return x
def num_flat_features(self, x):#定義子函數(shù)計算batch維度之外的向量參數(shù)個數(shù)
size = x.size()[1:] # all dimensions except the batch dimension
num_features = 1
for s in size:
num_features *= s
return num_features
net = Net()
print(net)
Out:
Net(
(conv1): Conv2d(1, 6, kernel_size=(3, 3), stride=(1, 1))
(conv2): Conv2d(6, 16, kernel_size=(3, 3), stride=(1, 1))
(fc1): Linear(in_features=576, out_features=120, bias=True)
(fc2): Linear(in_features=120, out_features=84, bias=True)
(fc3): Linear(in_features=84, out_features=10, bias=True)
)
params = list(net.parameters())
print(len(params))
print(params[0].size()) # conv1's .weight
Out:
10
torch.Size([6, 1, 3, 3])
下一步為了防止每次反向傳播，梯度累加脸甘，需要梯度初始化為0
net.zero_grad()#所有參數(shù)梯度清零
out.backward(torch.randn(1, 10))#反向傳播的過程只需要調(diào)用loss.backgrad()函數(shù)即可
注意：
torch.nn only supports mini-batches. The entire torch.nn package only supports inputs that are a mini-batch of samples, and not a single sample.即不支持單張圖像輸入訓練
例如,nn.Conv2d只接受4維的張量:
[nSamples ,nChannels, Height ,Width]
如果只有單個樣本,那么使用input.unsqueeze(0)來增加假的batch維度.
